首页> 外文会议>International Joint Conference on Neural Networks >Visual Navigation with Actor-Critic Deep Reinforcement Learning
【24h】

Visual Navigation with Actor-Critic Deep Reinforcement Learning

机译:视觉导航与演员关键深度强化学习

获取原文

摘要

Visual navigation in complex environments is crucial for intelligent agents. In this paper, we propose an efficient deep reinforcement learning (DRL) method to tackle visual navigation tasks. We present the synchronous advantage actor-critic (A2C) with generalized advantage estimator (GAE) algorithm. The A2C enables agents to learn from multiple processes, which significantly reduces the training time. The GAE used to estimate the advantage function improves the policy gradient estimates. We focus on visual navigation tasks in ViZDoom, and train agents in two health gathering scenarios. The experimental results show this method successfully teaches our agents to navigate in these scenarios. The A2C with GAE agent reaches the highest score in the first task, and a competitive score in the second task. In addition, this agent has better average scores and lower variances in both tasks.
机译:复杂环境中的视觉导航对于智能代理至关重要。在本文中,我们提出了一种有效的深度加强学习(DRL)方法来解决视觉导航任务。我们介绍了具有广义优势估计器(GAE)算法的同步优势演员 - 评论家(A2C)。 A2C使代理能够从多个过程中学习,这显着降低了培训时间。用于估计优势函数的GAE改善了政策梯度估计。我们专注于Vizoom中的视觉导航任务,并在两个健康聚集方案中的火车代理。实验结果表明,这种方法成功地教导了我们的代理商在这些方案中导航。与GAE代理的A2C达到了第一任务中的最高分,以及第二个任务中的竞争分数。此外,该代理商在两个任务中具有更好的平均分数和较低的差异。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号